Skip to content

neural net framework in vanilla python, with some demo applications and analysis

Notifications You must be signed in to change notification settings

jeremy-dolan/neural-net-from-scratch

Repository files navigation

Neural Net From Scratch

Machine learning frameworks, with some demo applications and analysis.

  • mlp_framework_vanilla.py - Complete multilayer perceptron neural network framework, written in vanilla Python for educational purposes. It is well commented and wildly inefficient. 🙃
    • Demo: XOR and linear separability - This notebook discusses the XOR function and linear separability. We construct a multi-layer perceptron that learns XOR, and then analyze the trained network and graph its decision boundaries.
      Teaser image

    • Demo: Digit classifier - This notebook trains a multi-class digit classifier using the MNIST dataset, and features a couple of interesting visualizations. Planned addition: an interactive ipynb widget for drawing digits with real-time visualization of the predicted probability distribution.
      Teaser image

About

neural net framework in vanilla python, with some demo applications and analysis

Resources

Stars

Watchers

Forks